The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 556
D. Hidayat
daffahidayat
·
AI & ML interests
Board games and backpropagation
Recent Activity
updated a model 5 days ago
daffahidayat/contrastive-test published a model 5 days ago
daffahidayat/contrastive-test liked a model 5 days ago
BAAI/bge-small-en-v1.5Organizations
None yet
upvoted 2
papers 10 days ago